ModelLing 3.2-Flash / 百灵 Ling 3.2-Flash
Ling 3.2-Flash
A natively multimodal large model released by Ant Ling, built on a Mixture-of-Experts architecture with 560B total parameters and 25B activated per token. According to official evaluations, it exceeds Opus 5 Max on three benchmarks.
Timeline (last 90 days)
Nov 8
Ant Ling released the native multimodal model Ling 3.2-Flash, with 560B total parameters and 25B activated per token.
Unverified50%
Nov 8
In Ant Ling's official evaluations, Ling 3.2-Flash scored higher than Opus 5 Max on all three benchmarks.
Unverified50%